Arabic sign language continuous sentences recognition using PCNN and graph matching

Many previous researchers have tried developing sign languages recognition systems in general and Arabic sign language specifically. They succeeded to achieve acceptable results for isolated gestures level, but none of them investigated the recognition of connected sequence of gestures. This paper focuses on how to recognize real-time connected sequence of gestures using graph-matching technique, also how the continuous input gestures are segmented and classified. Graphs are a general and powerful data structure useful for the representation of various objects and concepts. This work is a component of a real-time Arabic Sign Language Recognition system that applied pulse-coupled neural network for static posture recognition in its first phase. This work can be adapted and applied to different sign languages and other recognition problems.     

Damping controller design for power system oscillations usingglobal signals

This paper describes a new power system stabilizer (PSS) design for damping power system oscillations focusing on interarea modes. The input to the PSS consists of two signals. The first signal is mainly to damp the local mode in the area where PSS is located using the generator rotor speed as an input signal. The second is an additional global signal for damping interarea modes. Two global signals are suggested; the tie-line active power and speed difference signals. The choice of PSS location, input signals and tuning is based on modal analysis and frequency response information. These two signals can also be used to enhance damping of interarea modes using SVC located in the middle of the transmission circuit connecting the two oscillating groups. The effectiveness and robustness of the new design are tested on a 19-generator system having characteristics and structure similar to the Western North American grid     

3D object recognition technique using multiple 2D views for Arabic sign language

Some objects in specific poses cannot be distinguished using a single view. A model is proposed and developed for 3D object recognition based on multiple-views; it was applied on hand postures recognition. A pulse-coupled neural network is used to generate features vector for single view. Two views with different view angles are used; each view generates its features’ vector. The two 2D-vectors are then linearly combined into one 3D vector. The hand postures are then combined to construct a dynamic gesture (word). The reconstruction is performed using best-match search algorithm. The experiment was conducted on 50 words and the result was 96% recognition accuracy confirming objects dataset offline extendibility.